Abstract:High-precision 3D maps play an important role in autonomous driving. The current mapping system performs well in most circumstances. However, it still encounters difficulties in the case of the Global Navigation Satellite System (GNSS) signal blockage, when surrounded by too many moving objects, or when mapping a featureless environment. In these challenging scenarios, either the global navigation approach or the local navigation approach will degenerate. With the aim of developing a degeneracy-aware robust ma… Show more
“…However, a long corridor or structured pipes are still a challenge for these methods. The authors of [28,29] proposed to use the RADAR SLAM system in combination with GNSS to reconstruct the areas with repeated textures. However, once the GNSS signal disappears, the system is difficult to operate and the signal is nearly absent underground, in tunnels and mines, and in building interiors.…”
In recent years, there has been a growing demand for 3D reconstructions of tunnel pits, underground pipe networks, and building interiors. For such scenarios, weak textures, repeated textures, or even no textures are common. To reconstruct these scenes, we propose covering the lighting sources with films of spark patterns to “add” textures to the scenes. We use a calibrated camera to take pictures from multiple views and then utilize structure from motion (SFM) and multi-view stereo (MVS) algorithms to carry out a high-precision 3D reconstruction. To improve the effectiveness of our reconstruction, we combine deep learning algorithms with traditional methods to extract and match feature points. Our experiments have verified the feasibility and efficiency of the proposed method.
“…However, a long corridor or structured pipes are still a challenge for these methods. The authors of [28,29] proposed to use the RADAR SLAM system in combination with GNSS to reconstruct the areas with repeated textures. However, once the GNSS signal disappears, the system is difficult to operate and the signal is nearly absent underground, in tunnels and mines, and in building interiors.…”
In recent years, there has been a growing demand for 3D reconstructions of tunnel pits, underground pipe networks, and building interiors. For such scenarios, weak textures, repeated textures, or even no textures are common. To reconstruct these scenes, we propose covering the lighting sources with films of spark patterns to “add” textures to the scenes. We use a calibrated camera to take pictures from multiple views and then utilize structure from motion (SFM) and multi-view stereo (MVS) algorithms to carry out a high-precision 3D reconstruction. To improve the effectiveness of our reconstruction, we combine deep learning algorithms with traditional methods to extract and match feature points. Our experiments have verified the feasibility and efficiency of the proposed method.
“…With advancements in fields such as autonomous driving [1], digital twins [2,3], cultural heritage preservation [4], and humanities research and education [5], the importance of 3D reconstruction has become increasingly paramount. There are numerous methods for 3D reconstruction, including active reconstruction techniques like LiDAR, synthetic aperture radar (SAR), Time-of-Flight (TOF), and structured light cameras, as well as passive reconstruction methods based on vision cameras [6][7][8][9][10]. Compared to active reconstruction methods such as LiDAR and TOF, visual 3D reconstruction offers several advantages including ease of use, richness of information, and cost-effectiveness.…”
The task of 3D reconstruction of urban targets holds pivotal importance for various applications, including autonomous driving, digital twin technology, and urban planning and development. The intricate nature of urban landscapes presents substantial challenges in attaining 3D reconstructions with high precision. In this paper, we propose a semantically aware multi-view 3D reconstruction method for urban applications which incorporates semantic information into the technical 3D reconstruction. Our research primarily focuses on two major components: sparse reconstruction and dense reconstruction. For the sparse reconstruction process, we present a semantic consistency-based error filtering approach for feature matching. To address the challenge of errors introduced by the presence of numerous dynamic objects in an urban scene, which affects the Structure-from-Motion (SfM) process, we propose a computation strategy based on dynamic–static separation to effectively eliminate mismatches. For the dense reconstruction process, we present a semantic-based Semi-Global Matching (sSGM) method. This method leverages semantic consistency to assess depth continuity, thereby enhancing the cost function during depth estimation. The improved sSGM method not only significantly enhances the accuracy of reconstructing the edges of the targets but also yields a dense point cloud containing semantic information. Through validation using architectural datasets, the proposed method was found to increase the reconstruction accuracy by 32.79% compared to the original SGM, and by 63.06% compared to the PatchMatch method. Therefore, the proposed reconstruction method holds significant potential in urban applications.
“…Optical techniques have been widely used for three-dimensional (3D) measurements in broad areas of applications, especially in the manufacturing industry for inspection and monitoring [1][2][3][4] , biomedical imaging 5 , autonomous driving 6 , and arts and cultural heritage protection 7 . Inspection and reconstruction of transparent and translucent objects with steep slopes still pose a tough challenge 8 as there is no significant change in the intensity of light passing through.…”
Due to the advancements in the field of optical metrology, it has found its applications in various areas such as biomedical, automotive, semiconductors, aerospace, etc. The popularity of optical techniques for metrology has increased by multiple folds owing to its non-invasive nature with ease of setup, fast data acquisition, and remote sensing ability. Optical techniques include hologram interferometry, speckle photography, speckle interferometry, moire interferometry, photoelasticity, fringe projection technique, etc. The holographic interferometry technique works by quantifying the optical phase of the object by measuring the change in the interference fringes due to the shape of an object. This technique has a large number of advantages, but a steep object leads to a large number of fringes in the field of view, which are not resolvable as they fail to satisfy the Nyquist criterion. In this work, the fringe projection technique, which is a noninterferometric, non-invasive technique for generating 3D surface information is employed to measure the shape of a phase object like a wedge. Fringe projection is presented as a robust and compact technique for shape measurement of phase objects as it utilizes lesser components and has less complexity compared to the holographic technique.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.